浏览全部资源
扫码关注微信
Received：14 August 2020，
Revised：2020-10-14，
Accepted：21 October 2020，
Published：16 January 2021
移动端阅览
随着汽车智能化程度的不断提高，智能汽车通过环境传感器与周边行驶环境的信息交互与互联更为密切，需应对的行驶环境状况也越来越复杂，包括行驶道路、周边交通和气象条件等诸多因素，具有较强的不确定性、难以重复、不可预测和不可穷尽。限于研发周期和成本、工况复杂多样性，特别是安全因素的考虑，传统的开放道路测试试验或基于封闭试验场的测试难以满足智能驾驶系统可靠性与鲁棒性的测试要求。因此，借助数字虚拟技术的仿真测试成为智能驾驶测试验证一种新的手段，仿真场景的构建作为模拟仿真的重要组成部分，是实现智能驾驶测试中大样本、极限边界小概率样本测试验证的关键技术，这对提升智能驾驶系统的压力和加速测评水平显得尤为重要。面向智能驾驶测试的仿真场景构建技术已成为当前汽车智能化新的研究课题和世界性的研究热点，作为一种新兴技术仍面临许多挑战。本文提出了面向智能驾驶测试的仿真场景构建方法，系统阐述了国内外研究工作的进展与现状，包括场景自动构建方法和交通仿真建模方法，重点分析一些值得深入研究的问题并围绕场景构建技术的发展趋势进行了讨论分析，最后介绍了团队相关研究在2020中国智能驾驶挑战赛仿真赛和世界智能驾驶挑战赛的仿真场景应用情况。
With the continuous improvement of vehicle intelligence
the interaction of vehicles with the surrounding environment through perception is increasing. The environment that needs to be dealt with
including many factors such as roads
surrounding traffic and weather conditions
is becoming increasing complex. Limited by the development cycle and cost
especially safety factors and the consideration of complex and diverse working conditions
traditional open road or closed field tests are difficult to meet the requirements of intelligent driving testing. Therefore
simulation test based on digital virtual technology has become a new important means for intelligent driving testing and verification. The simulation test mainly adopts a combination of accurate physical modeling
efficient numerical simulation
and high-fidelity image rendering to realistically construct human-vehicle environment models
including vehicles
roads
weather and lighting
and traffic
and various types of vehicles. The construction of virtual scenarios is a key technology simulation and is particularly important for improving the pressure and acceleration of intelligent driving testing. The virtual scenarios can meet the needs of a large number of diverse test samples to reflect the complex and changeable application environment of intelligent driving. They can also provide a large number of labeled datasets for machine learning that can contain rich data with boundary feature scenario content and lay a solid data foundation for deep learning perception and reinforcement learning planning algorithms. Therefore
the simulation scenario construction technology for intelligent driving test has been investigated worldwide in the current automotive intelligence. As an emerging technology
it still faces many challenges
and its methods need to be studied in depth. This paper systematically expounds the progress and current situation of domestic and foreign studies in simulation scenario construction technology
including automatic scenario construction methods and traffic simulation modeling methods
and focuses on some issues worthy of in-depth study. In the research of scenario construction methods
the key elements and characteristics of the limited scenarios can reflect the infinite richness and complex driving environment. A deep understanding of the network structure and mutual coupling of the scenario is essential for the research of virtual scenario construction. Establishing a description method of the scenario limit and boundary characteristics to form the scenario automated generation method can maximize the potential of accelerated testing of intelligent driving. Researchers have promoted the rapid development of scenario generation technology from different perspectives. However
they often use parameter traversal search ideas to determine the system state space. The development and testing is time consuming and labor intensive due to the unlimited expansion of scenario search. The construction of a scenario with dangerous characteristics requires in-depth exploration of the safety boundary of the ego vehicle driving. Thus
the constructed corner scenario can provide effective information corresponding to real driving for realizing the enhanced generation of the corner characteristics of the scenario. This condition responds to the accelerated testing of intelligent driving systems above level four. In terms of traffic modeling methods
a deep understanding of the driving behavior and interaction characteristics of vehicles is the basis and primary task. Determining the influence law of vehicle driving motion in data information and establishing the traffic model with random dangerous characteristics are the key to realize intelligent driving testing. The current data-driven traffic simulation modeling research mainly describes the microscopic behavior of traffic
but the accurate and true description of driving behavior characteristics is insufficient. The model input is the mutual movement relationship between the vehicle and the surrounding vehicles
and the model output is the speed or trajectory of the vehicle's movement. However
the diversity of results mainly depends on the amount of input data. If the amount of input data is small
the simulation results are monotonous
relying excessively on input data
and lack versatility. Simulating the motion and interaction behavior of different types of agents in a heterogeneous environment is difficult
especially at traffic intersections. At present
replacing the role of physical mechanism models in generality is difficult. This paper introduces the application of PanoSim simulation platform developed by our team and the related research in 2020 China Intelligent Driving Challenge and World Intelligent Driving Challenge. The intelligent driving challenge is based on a variety of scenarios and traffic environments built by the PanoSim simulation environment. This condition allows participating teams to access the simulation scenario database for obtaining vehicle-mounted sensor information in the simulation environment
such as camera video streams
millimeter wave radar data
lidar point cloud data
and true value information. The simulation scenarios of the intelligent driving challenge are mainly divided into two categories: decision-control and perception-decision-control groups. With the continuous development of computer software and hardware
real-time graphics and image processing
virtual reality
especially parallel processing and image rendering and other simulation technologies
and the environment simulation
and sensor modeling technology
the simulation technology for vehicle testing will become the key factor of vehicle intelligent driving technology
product development
and core competency of technology and products.
Althoff M and Lutz S. 2018. Automatic generation of safety-critical test scenarios for collision avoidance of road vehicles//Proceedings of 2018 IEEE Intelligent Vehicles Symposium (Ⅳ). Changshu, China: IEEE: 1326-1333[ DOI: 10.1109/IVS.2018.8500374 http://dx.doi.org/10.1109/IVS.2018.8500374 ]
Brockman G, Cheung V, Pettersson L, Schneider J, Schulman J, Tang J and Zaremba W. 2016. OpenAI gym[EB/OL ] .[2020-07-14 ] . https://arxiv.org/pdf/1606.01540.pdf https://arxiv.org/pdf/1606.01540.pdf
Butakov V A and Ioannou P. 2015. Personalized driver/vehicle lane change models for ADAS. IEEE Transactions on Vehicular Technology, 64(10):4422-4431[DOI:10.1109/TVT.2014.2369522]
Chao Q W, Deng Z G, Ren J P, Ye Q Q and Jin X G. 2018. Realistic data-driven traffic flow animation using texture synthesis. IEEE Transactions on Visualization and Computer Graphics, 24(2):1167-1178[DOI:10.1109/TVCG.2017.2648790]
Corso A, Du P, Driggs-Campbell K and Kochenderfer M J. 2019. Adaptive stress testing with reward augmentation for autonomous vehicle validation//Proceedings of 2019 IEEE Intelligent Transportation Systems Conference (ITSC). Auckland, New Zealand: IEEE: 163-168[ DOI: 10.1109/ITSC.2019.8917242 http://dx.doi.org/10.1109/ITSC.2019.8917242 ]
Hallerbach S, Xia Y, Eberle U and Koester F. 2018. Simulation-based identification of critical scenarios for cooperative and automated vehicles. SAE International Journal of Connected and Automated Vehicles, 1(2):93-106[DOI:10.4271/2018-01-1066]
Jordao K, Pettré J, Christie M and Cani M P. 2014. Crowd sculpting:a space-time sculpting method for populating virtual environments. Journal of Computer Graphics Forum, 33(2):351-360[DOI:10.1111/cgf.12316]
Kehrer M, Pitz J, Rothermel T and Reuss HC. 2018. Framework for interactive testing and development of highly automated driving functions//The 18th Internationales Stuttgarter Symposium. Wiesbaden, Germany: Springer Vieweg, 659-669[ DOI: 10.1007/978-3-658-21194-3_51 http://dx.doi.org/10.1007/978-3-658-21194-3_51 ]
Kesting A, Treiber M and Helbing D. 2007. General lane-changing model MOBIL for car-following models. Journal of the Transportation, Research Board, 1999(1):86-94[DOI:10.3141/1999-10]
Kim S, Bera A, Bes A, Chabra R and Manocha D. 2016. Interactive and adaptive data-driven crowd simulation//Proceedings of 2016 IEEE Virtual Reality (VR). Greenville, USA: IEEE: 29-38[ DOI: 10.1109/VR.2016.7504685 http://dx.doi.org/10.1109/VR.2016.7504685 ]
Klischat M and Althoff M. 2019. Generating critical test scenarios for automated vehicles with evolutionary algorithms//2019 IEEE Intelligent Vehicles Symposium (Ⅳ). Paris, France: IEEE: 2352-2358[ DOI: 10.1109/IVS.2019.8814230 http://dx.doi.org/10.1109/IVS.2019.8814230 ]
Klueck F, Li Y H, Nica M, Tao J B and Wotawa F. 2018. Using ontologies for test suites generation for automated and autonomous driving functions//2018 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW). Memphis, USA: IEEE: 118-123[ DOI: 10.1109/ISSREW.2018.00-20 http://dx.doi.org/10.1109/ISSREW.2018.00-20 ]
Koren M, Alsaif S, Lee R and Kochenderfer M J. 2018. Adaptive stress testing for autonomous vehicles//2018 IEEE Intelligent Vehicles Symposium (Ⅳ). Changshu, China: IEEE: 1-7[ DOI: 10.1109/IVS.2018.8500400 http://dx.doi.org/10.1109/IVS.2018.8500400 ]
Langner J, Bach J, Ries L, Otten S, Holzäpfel M and Sax E. 2018. Estimating the uniqueness of test scenarios derived from recorded real-world-driving-data using autoencoders//2018 IEEE Intelligent Vehicles Symposium (Ⅳ). Changshu, China: IEEE: 1860-1866[ DOI: 10.1109/IVS.2018.8500464 http://dx.doi.org/10.1109/IVS.2018.8500464 ]
Li C X, Cao L, Chen X L, Zhang Y L, Xu Z X, Peng H and Duan L W. 2018. Cloud reasoning model-based exploration for deep reinforcement learning. Journal of Electronics and Information Technology, 40(1):244-248
李晨溪, 曹雷, 陈希亮, 张永亮, 徐志雄, 彭辉, 段理文. 2018.基于云推理模型的深度强化学习探索策略研究.电子与信息学报, 40(1):244-248
Menzel T, Bagschik G and Maurer M. 2018. Scenarios for development, test and validation of automated vehicles//2018 IEEE Intelligent Vehicles Symposium (Ⅳ). Changshu, China: IEEE: 1821-1827[ DOI: 10.1109/IVS.2018.8500406 http://dx.doi.org/10.1109/IVS.2018.8500406 ]
Oyler D W, Yildiz Y, Girard A R, Li N I and Kolmanovsky I V. 2016. A game theoretical model of traffic with multiple interacting drivers for use in autonomous vehicle development//Proceedings of 2016 American Control Conference (ACC). Boston, USA: IEEE: 1705-1710[ DOI: 10.1109/ACC.2016.7525162 http://dx.doi.org/10.1109/ACC.2016.7525162 ]
Punzo V, Montanino M and Ciuffo B. 2015. Do we really need to calibrate all the parameters? Variance-based sensitivity analysis to simplify microscopic traffic flow models. IEEE Transactions on Intelligent Transportation Systems, 16(1):184-193[DOI:10.1109/TITS.2014.2331453]
Ren J P, Xiang W, Xiao Y X, Yang R G, Manocha D and Jin X G. 2019. Heter-Sim:heterogeneous multi-agent systems simulation by interactive data-driven optimization. IEEE Transactions on Visualization and Computer Graphics(Early Access), 25(8):1-15[DOI:10.1109/TVCG.2019.2946769]
Sewall J, Wilkie D and Lin M C. 2011. Interactive hybrid simulation of large-scale traffic//Proceedings of 2011 SIGGRAPH Asia Conference. New York, USA: ACM: #135[ DOI: 10.1145/2024156.2024169 http://dx.doi.org/10.1145/2024156.2024169 ]
Stark L, Obst S, Schoenawa S and Düring M. 2019. Towards vision zero: addressing white spots by accident data based ADAS design and evaluation//Proceedings of 2019 IEEE International Conference on Vehicular Electronics and Safety (ICVES). Cairo, Egypt: IEEE: 1-6[ DOI: 10.1109/ICVES.2019.8906409 http://dx.doi.org/10.1109/ICVES.2019.8906409 ]
Tang S, Li N, Kolmanovsky I and Girard A. 2020. Trajectory optimization for falsification:a case study of vehicle rollover test generation based on black-box models//IFAC World Congress. Berlin, Germany:IFAC, 2020:1-6
Tatar M. 2016. Test and validation of advanced driver assistance systems automated search for critical scenarios. ATZelektronik Worldwide, 11:54-57[DOI:10.1007/s38314-015-0574-1]
Treiber M, Hennecke A and Helbing D. 2000. Congested traffic states in empirical observations and microscopic simulations. Physical Review E, 62(2):1805-1824[DOI:10.1103/PhysRevE.62.1805]
Ulbrich S, Menzel T, Reschka A, Schuldt F and Maurer M. 2015. Defining and substantiating the terms scene, situation, and scenario for automated driving//Proceedings of the 18th IEEE International Conference on Intelligent Transportation Systems. Las Palmas, Spain: IEEE: 982-988[ DOI: 10.1109/ITSC.2015.164 http://dx.doi.org/10.1109/ITSC.2015.164 ]
Wei D L and Liu H C. 2013. Analysis of asymmetric driving behavior using a self-learning approach. Transportation Research Part B:Methodological, 47:1-14[DOI:10.1016/j.trb.2012.09.003]
Wu B, Zhu X C, Shen J P and Sun X Y. 2018. Analysis of causation of rear-end incidents based on naturalistic driving study. Journal of Tongji University (Natural Science), 46(9):1253-1260
吴斌, 朱西产, 沈剑平, 孙晓宇. 2018.基于自然驾驶研究的直行追尾危险场景诱导因素分析.同济大学学报(自然科学版), 46(9):1253-1260
Xia Q, Duan J, Gao F, Chen T and Yang C. 2017. Automatic generation method of test scenario for ADAS based on complexity[EB/OL ] .[2020-07-14 ] . https://saemobilus.sae.org/content/2017-01-1992/ https://saemobilus.sae.org/content/2017-01-1992/
Xie D F, Fang Z Z, Jia B and He Z B. 2019. A data-driven lane-changing model based on deep learning. Transportation Research Part C:Emerging Technologies, 106:41-60[DOI:10.1016/j.trc.2019.07.002]
Yan Y L, Zhu X C, Liao M Z and Ma Z X. 2018. Danger degree evaluation method of crossroad scenario based on naturalistic driving analysis//Proceedings of the 21st International Conference on Intelligent Transportation Systems (ITSC). Maui, USA: IEEE: 1435-1440[ DOI: 10.1109/ITSC.2018.8569328 http://dx.doi.org/10.1109/ITSC.2018.8569328 ]
Yu S W, Liu Q L and Li X H. 2013. Full velocity difference and acceleration model for a car-following theory. Communications in Nonlinear Science and Numerical Simulation, 18(5):1229-1234[DOI:10.1016/j.cnsns.2012.09.014]
Zhao D, Huang X, Peng H, Lam H and LeBlanc D J. 2018. Accelerated evaluation of automated vehicles in car-following maneuvers. IEEE Transactions on Intelligent Transportation Systems, 19(3):733-744[DOI:10.1109/TITS.2017.2701846]
Zhao D, Peng H, Bao S, Nobukawa K, LeBlanc D J and Pan C S. 2016. Accelerated evaluation of automated vehicles using extracted naturalistic driving data. The Dynamics of Vehicles on Roads and Tracks, 18(3):287-296[DOI:10.1201/b21185-33]
Zhu B, Zhang P X, Zhao J, Chen H, Xu Z G, Zhao X M and Deng W W. 2019. Review of scenario-based virtual validation methods for automated vehicles. China Journal of Highway and Transport, 32(6):1-19
朱冰, 张培兴, 赵健, 陈虹, 徐志刚, 赵祥模, 邓伟文. 2019.基于场景的自动驾驶汽车虚拟测试研究进展.中国公路学报, 32(6):1-19)[DOI:10.19721/j.cnki.1001-7372.2019.06.001]
相关文章
相关作者
相关机构
京公网安备11010802024621
